Towards Surgical World-Action Modeling: A Preliminary Joint Visual-Trajectory Forecasting for Surgical Motion Planning
2026-08-20 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionRobotics
AI summaryⓘ
The authors created a model that can predict both how surgical tools will move and how the surgery scene will look in the future, based on past video and tool movements. Unlike earlier methods that handled tool paths and scene visuals separately, their joint approach better links the predicted tool motions with visual changes. Their model uses a step-by-step method to make more accurate short-term predictions, but errors and blurry visuals still grow when predicting further ahead. This shows early promise but also highlights challenges in accurately modeling surgical actions over longer times.
surgical planningtrajectory predictionvideo frame encodinglatent representationtemporal-spatial encoderautoregressive predictionPSNRADEworld-action modelingvisual forecasting
Authors
Weiliang Huang, Huanrong Liu, Bob Zhang, Qi Dou, Zhen Chen, Yun Gu, Guy Rosman, Qingbiao Li
Abstract
Reliable surgical planning requires models to anticipate not only how instruments will move, but also how the operative visual state will evolve together with such motion. Existing approaches typically treat future scene generation and instrument trajectory prediction as two separate tasks. Scene-only models cannot directly evaluate the accuracy of future instrument motion at the trajectory level, while trajectory-only models fail to capture the visual consequences of instrument movement, leaving the consistency between predicted trajectories and future scene evolution unaddressed. Jointly forecasting both provides a more complete account of surgical action-scene dynamics by enabling explicit trajectory-level evaluation while simultaneously modeling the corresponding visual evolution. To bridge this gap, we present a preliminary joint visual-trajectory world-action model that simultaneously forecasts future visual states and instrument trajectories from historical surgical observations. Specifically, we encode historical video frames and tool trajectories into latent representations, which are processed by a temporal-spatial encoder and subsequently decoded through separate visual-state and trajectory prediction heads. Based on this preliminary architecture, a chunked autoregressive rollout is repeatedly applied to predict fifteen future steps. The chunked strategy consistently outperforms direct one-shot prediction across all evaluated horizons, improving first-segment PSNR from 18.86 to 23.11 dB and reducing ADE from 45.77 to 22.22 pixels. These results demonstrate the initial feasibility of joint visual-motion forecasting. However, we observe progressive visual degradation and accumulated trajectory errors over longer prediction horizons, which remain important challenges for future surgical world-action modeling.